Biometric data processing for a security system

Abstract

A computing system may perform image processing on image data acquired by a camera at a property to determine at least a first feature of the image data. Based at least in part on a determination that the first feature satisfies a rule, the computing system may generate a vector representing a plurality of characteristics of a face represented in the image data. The vector may then be used to determine a particular person is represented in the image data.

1 . A method, comprising:
 receiving, by a computing system, a first request to create a profile for a person;   determining, by the computing system, an identifier for the person;   based at least in part on the first request, causing, by the computing system, a second request to be sent to a first application corresponding to the identifier, the second request seeking authorization from the person to use of biometric facial recognition using one or more images of the person;   receiving, by the computing system, a response to the second request, the response indicating that the person has authorized use of biometric facial recognition using one or more images of the person;   determining, by the computing system, at least a first image of a first face the person; and   based at least in part on the response, generating, by the computing system and using the first image, a first vector representing a plurality of characteristics of the first face.   
     
     
         2 . The method of  claim 1 , wherein the identifier comprises an email address or phone number of the person. 
     
     
         3 . The method of  claim 1 , further comprising:
 generating, by the computing system, a second vector representing the plurality of characteristics of a second face represented in image data acquired by a camera;   determining, by the computing system, that the second vector corresponds to the first vector; and   determining, by the computing system, that the person is represented in the image data based at least in part on the second vector corresponding to the first vector.   
     
     
         4 . The method of  claim 3 , wherein the first request is received from a second application executing under control of an endpoint device associated with a property monitored by the computing system, and the method further comprises:
 storing, by the computing system and in a datastore, at least first data representing an image of the second face;   based at least in part on the computing system determining that the person is represented in the image data, storing, by the computing system and in the datastore, second data in association with the first data, the second data indicating that the image of the second face corresponds to the person; and   based at least in part on the first data and the second data having been stored in the datastore, causing the second application to output an indication that the image of the second face corresponds to the person.   
     
     
         5 . The method of  claim 1 , wherein generating the first vector comprises generating a biometric embedding for the first face. 
     
     
         6 . The method of  claim 1 , wherein the first request is received from a second application executing under control of an endpoint device associated with a property monitored by the computing system. 
     
     
         7 . A system, comprising:
 one or more processors; and   one or more computer-readable mediums encoded with instructions which, when executed by the one or more processors, cause the system to:
 receive a first request to create a profile for a person; 
 determine an identifier for the person; 
 based at least in part on the first request, cause a second request to be sent to a first application corresponding to the identifier, the second request seeking authorization from the person to use of biometric facial recognition using one or more images of the person; 
 receive a response to the second request, the response indicating that the person has authorized use of biometric facial recognition using one or more images of the person; 
 determine at least a first image of a first face the person; and 
 based at least in part on the response, generate, using the first image, a first vector representing a plurality of characteristics of the first face. 
   
     
     
         8 . The system of  claim 7 , wherein the identifier comprises an email address or phone number of the person. 
     
     
         9 . The system of  claim 7 , wherein the one or more computer-readable mediums are further encoded with additional instructions which, when executed by the one or more processors, further cause the system to:
 generate the first vector at least in part by generating a biometric embedding for the first face.   
     
     
         10 . The system of  claim 7 , wherein the one or more computer-readable mediums are further encoded with additional instructions which, when executed by the one or more processors, further cause the system to:
 generate a second vector representing the plurality of characteristics of a second face represented in image data acquired by a camera;   determine that the second vector corresponds to the first vector; and   determine that the person is represented in the image data based at least in part on the second vector corresponding to the first vector.   
     
     
         11 . The system of  claim 10 , wherein the one or more computer-readable mediums are further encoded with additional instructions which, when executed by the one or more processors, further cause the system to:
 receive the first request from a second application executing under control of an endpoint device associated with a property monitored by the system;   store, in a datastore, at least first data representing an image of the second face;   based at least in part on the system determining that the person is represented in the image data, store, in the datastore, second data in association with the first data, the second data indicating that the image of the second face corresponds to the person; and   based at least in part on the first data and the second data having been stored in the datastore, cause the second application to output an indication that the image of the second face corresponds to the person.   
     
     
         12 . The system of  claim 7 , wherein the one or more computer-readable mediums are further encoded with additional instructions which, when executed by the one or more processors, further cause the system to:
 receive the first request from a second application executing under control of an endpoint device associated with a property monitored by the system.   
     
     
         13 . One or more non-transitory computer-readable mediums encoded with instructions which, when executed by one or more processors of a system, cause the system to:
 receive a first request to create a profile for a person;   determine an identifier for the person;   based at least in part on the first request, cause a second request to be sent to a first application corresponding to the identifier, the second request seeking authorization from the person to use of biometric facial recognition using one or more images of the person;   receive a response to the second request, the response indicating that the person has authorized use of biometric facial recognition using one or more images of the person;   determine at least a first image of a first face the person; and   based at least in part on the response, generate, using the first image, a first vector representing a plurality of characteristics of the first face.   
     
     
         14 . The one or more non-transitory computer-readable mediums of  claim 13 , wherein the identifier comprises an email address or phone number of the person. 
     
     
         15 . The one or more non-transitory computer-readable mediums of  claim 13 , further encoded with additional instructions which, when executed by the one or more processors, further cause the system to:
 generate the first vector at least in part by generating a biometric embedding for the first face.   
     
     
         16 . The one or more non-transitory computer-readable mediums of  claim 13 , further encoded with additional instructions which, when executed by the one or more processors, further cause the system to:
 generate a second vector representing the plurality of characteristics of a second face represented in image data acquired by a camera;   determine that the second vector corresponds to the first vector; and   determine that the person is represented in the image data based at least in part on the second vector corresponding to the first vector.   
     
     
         17 . The one or more non-transitory computer-readable mediums of  claim 16 , further encoded with additional instructions which, when executed by the one or more processors, further cause the system to:
 receive the first request from a second application executing under control of an endpoint device associated with a property monitored by the system;   store, in a datastore, at least first data representing an image of the second face;   based at least in part on the system determining that the person is represented in the image data, store, in the datastore, second data in association with the first data, the second data indicating that the image of the second face corresponds to the person; and   based at least in part on the first data and the second data having been stored in the datastore, cause the second application to output an indication that the image of the second face corresponds to the person.   
     
     
         18 . The one or more non-transitory computer-readable mediums of  claim 13 , further encoded with additional instructions which, when executed by the one or more processors, further cause the system to:
 receive the first request from a second application executing under control of an endpoint device associated with a property monitored by the system.